LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images

TL;DR

LucidFusion introduces a novel framework for 3D reconstruction from unposed images by using relative coordinate maps and Gaussian representations, eliminating the need for explicit pose estimation and enabling fast, flexible 3D modeling.

Contribution

The paper presents Relative Coordinate Gaussians (RCG) and a new framework that reconstructs 3D objects from unposed images without explicit camera pose estimation, improving flexibility and speed.

Findings

Produces robust 3D reconstructions within seconds.

Handles arbitrary numbers of unposed images.

Eliminates reliance on explicit pose estimation.

Abstract

Recent large reconstruction models have made notable progress in generating high-quality 3D objects from single images. However, current reconstruction methods often rely on explicit camera pose estimation or fixed viewpoints, restricting their flexibility and practical applicability. We reformulate 3D reconstruction as image-to-image translation and introduce the Relative Coordinate Map (RCM), which aligns multiple unposed images to a main view without pose estimation. While RCM simplifies the process, its lack of global 3D supervision can yield noisy outputs. To address this, we propose Relative Coordinate Gaussians (RCG) as an extension to RCM, which treats each pixel's coordinates as a Gaussian center and employs differentiable rasterization for consistent geometry and pose recovery. Our LucidFusion framework handles an arbitrary number of unposed inputs, producing robust 3D reconstructions within seconds and paving the way for more flexible, pose-free 3D pipelines.